Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Vehicle driving behavior detection and early warning system and method based on deep learning

A deep learning and early warning system technology, applied in medical science, psychological devices, measuring pulse rate/heart rate, etc., can solve the problems of low equipment demand, affecting driving, and low detection accuracy, so as to achieve accurate judgment results and effective early warning Reliable, objective effect of acquisition accuracy

Pending Publication Date: 2019-07-02
YANGZHOU UNIV
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The detection algorithm based on physiological signal features has high accuracy, but it affects driving due to the contact between the sensor and the driver; the detection algorithm based on behavioral features does not require the driver to directly contact the detection device, and the equipment requirements are based on the existing devices of the car Low, very practical, but the detection accuracy is not high

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Vehicle driving behavior detection and early warning system and method based on deep learning
  • Vehicle driving behavior detection and early warning system and method based on deep learning
  • Vehicle driving behavior detection and early warning system and method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0093] combine figure 1 , the present invention is a vehicle-mounted driving behavior detection and early warning system based on deep learning, including the following:

[0094] In the embodiment of the present invention, the image acquisition module selects a camera to collect the driver's behavior video, and transmits the driver's behavior video collected by the camera to the control processing module through the USB communication module in the transmission module. Behaviors such as calling, smoking, driving with one hand, yawning, bowing the head, etc. of the subject to be tested are easy to perceive from the visual level, and the ratio of the closing time of human eyes to the total time in a period of time can be used to judge fatigue and can be used as a control process The information source for the module to perform comprehensive judgment on fatigue.

[0095] The heart rate acquisition module uses an optical heart rate sensor and a DA14580 chip. The optical heart rate...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a vehicle driving behavior detection and early warning system and method based on deep learning. The system includes an information collection module, a transmission module, acontrol processing module, and an early warning module; and the method includes the following steps: firstly collecting signal source information by the information collection module; then transmitting the collected signal source information to the control processing module through the transmission module; then judging a fatigue state and behavior of a to-be-detected object by the control processing module according to the signal source information; and transmitting a obtained result of the fatigue state and behavior to the early warning module and a cloud, and performing corresponding sound and light and vibration early warning by the early warning module according to the result of the fatigue state and behavior. The system and the method combine an image recognition technology of the deep learning, a physiological signal detection algorithm and a driving behavior detection algorithm to perform multi-signal source collection, and the collection accuracy is high; and determination of fatigue and behaviors of the to-be-detected object is performed by utilizing a machine learning-based data fusion algorithm, an obtained judgment result is more accurate, and early warning is more effective and reliable.

Description

technical field [0001] The invention belongs to the field of driving behavior detection, in particular to a vehicle-mounted driving behavior detection and early warning system and method based on deep learning. Background technique [0002] With the sustained and rapid development of my country's economy and society, the total number of motor vehicles in my country has increased dramatically. By the end of 2018, the number of motor vehicles in my country reached 322 million. The rapid increase of vehicles and the increase in the mileage of highways are increasing year by year, which is also accompanied by the frequent occurrence of accidental traffic accidents. At the same time, with the accelerated pace of life of modern people, the phenomenon of staying up late, lack of exercise, irregular diet and other factors have caused modern people to be prone to fatigue and poor energy, and fatigue driving will appear subsequently. According to statistics, among the factors that a...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): A61B5/18A61B5/00A61B5/024A61B5/0476A61B5/16G06K9/00
CPCA61B5/18A61B5/024A61B5/7455A61B5/746A61B5/7405A61B5/168A61B5/369G06V20/597
Inventor 曾心远张正华李斌韩雪胡新盛叶傲斌罗和成闻栋徐颖仪吕允博周立言
Owner YANGZHOU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products